Advertisement

Journal of Mechanical Science and Technology

, Volume 32, Issue 11, pp 5079–5088 | Cite as

Fault diagnosis method of rolling bearing using principal component analysis and support vector machine

  • Ying-Kui Gu
  • Xiao-Qing Zhou
  • Dong-Ping Yu
  • Yan-Jun Shen
Article
  • 5 Downloads

Abstract

To effectively extract the fault feature information of rolling bearings and improve the performance of fault diagnosis, a fault diagnosis method based on principal component analysis and support vector machine was presented, and the rolling bearings signals with different fault states were collected. To address the limitation on effectively dealing with the raw vibration signals by the traditional signal processing technology based on Fourier transform, wavelet packet decomposition was employed to extract the features of bearing faults such as outer ring flaking, inner ring flaking, roller flaking and normal condition. Compared with the previous literature on fault diagnosis using principal component analysis (PCA) and support vector machine (SVM), one-to-one and one-to-many algorithms were taken into account. Additionally, the effect of four kernel functions, such as liner kernel function, polynomial kernel function, radial basis function and hyperbolic tangent kernel function, on the performance of SVM classifier was investigated, and the optimal hype-parameters of SVM classifier model were determined by genetic algorithm optimization. PCA was employed for dimension reduction, so as to reduce the computational complexity. The principal components that reached more than 95 % cumulative contribution rate were extracted by PCA and were input into SVM and BP neural network classifiers for identification. Results show that the fault feature dimensionality of the rolling bearing is reduced from 8-dimensions to 5-dimensions, which can still characterize the bearing status effectively, and the computational complexity is reduced as well. Compared with the raw feature set, PCA has a higher fault diagnosis accuracy (more than 97 %), and a shorter diagnosis time relatively. To better verify the superiority of the proposed method, SVM classification results were compared with the results of BP neural network. It is concluded that SVM classifier achieved a better performance than BP neural network classifier in terms of the classification accuracy and time-cost.

Keywords

Principal component analysis Support vector machine Feature fusion Fault diagnosis Rolling bearing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    X. B. Xu, Y. C. Wang and C. L. Wen, Information–fusion method for fault diagnosis based on reliability evaluation of evidence, Control Theory & Applications, 28 (4) (2011) 504–510.Google Scholar
  2. [2]
    L. Y. Guan, Y. M. Shao, F. S. Gu, B. Fazenda and A. Ball, Gearbox fault diagnosis under different operating conditions based on time synchronous average and ensemble empirical mode decomposition, Iccas–Sice (2009) 383–388.Google Scholar
  3. [3]
    M. Kang, J. Kim, L. M. Wills and J. M. Kim, Time–varying and multiresolution envelope analysis and discriminative feature analysis for bearing fault diagnosis, IEEE Transactions on Industrial Electronics, 62 (12) (2015) 7749–7761.CrossRefGoogle Scholar
  4. [4]
    Y. Xu and S. Xiu, A new and effective method of bearing fault diagnosis using wavelet packet transform combined with support vector machine, J. of Computers, 6 (11) (2011) 2502–2509.Google Scholar
  5. [5]
    L. Meng, J. Xiang, Y. Zhong and W. Song, Fault diagnosis of rolling bearing based on second generation wavelet denoising and morphological filter, J. of Mechanical Science and Technology, 29 (8) (2015) 3121–3129.CrossRefGoogle Scholar
  6. [6]
    Z. Q. Li, X. P. Yan, C. Q. Yuan and Z. X. Peng, Intelligent fault diagnosis method for marine diesel engines using instantaneous angular speed, J. of Mechanical Science and Technology, 26 (8) (2012) 2413–2423.CrossRefGoogle Scholar
  7. [7]
    Z. P. Feng and M. J. Zuo, Vibration signal models for fault diagnosis of planetary gearboxes, J. of Sound and Vibration, 331 (22) (2012) 4919–4939.CrossRefGoogle Scholar
  8. [8]
    Y. G. Lei, Z. J. He, J. Lin, H. Dong and D. T. Kong, Research advances of fault diagnosis technique for planetary gearboxes, J. of Mechanical Engineering, 47 (19) (2011) 59–67.CrossRefGoogle Scholar
  9. [9]
    J. S. Lin and Q. Chen, Fault feature extraction of gearboxes based on multifractal detrended fluctuation analysis, J. of Vibration and Shock, 32 (2) (2013) 97–101.Google Scholar
  10. [10]
    W. G. Wang and L. Sun, Gearbox vibration signal fault feature extraction based on ensemble empirical mode decomposition and choi–williams distribution, Acta Armamentarii, 35 (8) (2014) 1288–1294.Google Scholar
  11. [11]
    Y. G. Lei, D. T. Kong, N. P. Li and J. Lin, Adaptive ensemble empirical mode decomposition and its application to fault detection of planetary gearboxes, J. of Mechanical Engineering, 50 (3) (2014) 64–70.CrossRefGoogle Scholar
  12. [12]
    H. C. Peng, F. H. Long and C. Ding, Feature selection based on mutual information: Criteria of max–dependency, max–relevance, and min–redundancy, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (8) (2005) 1226–1238.CrossRefGoogle Scholar
  13. [13]
    X. Y. Zhu, Y. Y. Zhang and Y. S. Zhu, Intelligent fault diagnosis of rolling bearing based on kernel neighborhood rough sets and statistical features, J. of Mechanical Science and Technology, 26 (9) (2012) 2649–2657.CrossRefGoogle Scholar
  14. [14]
    B. Otman and X. H. Yuan, Engine fault diagnosis based on multi–sensor information fusion using Dempster–Shafer evidence theory, Information Fusion, 8 (4) (2007) 379–386.CrossRefGoogle Scholar
  15. [15]
    G. M. Lim, D. M. Bae and J. H. Kim, Fault diagnosis of rotating machine by thermography method on support vector machine, J. of Mechanical Science and Technology, 28 (8) (2014) 2947–2952.CrossRefGoogle Scholar
  16. [16]
    Z. Q. Xing, J. F. Qu, Y. Chai, Q. Tang and Y. M. Zhou, Gear fault diagnosis under variable conditions with intrinsic timescale decomposition–singular value decomposition and support vector machine, J. of Mechanical Science and Technology, 31 (2) (2017) 545–553.CrossRefGoogle Scholar
  17. [17]
    H. Z. Huang, H. K. Wang, Y. F. Li, L. Zhang and Z. Liu, Support vector machine based estimation of remaining useful life: Current research status and future trends, J. of Mechanical Science and Technology, 29 (1) (2015) 151–163.CrossRefGoogle Scholar
  18. [18]
    Y. Li, W. Zhang, Q. Xiong, D. Luo, G. Mei and T. Zhang, A rolling bearing fault diagnosis strategy based on improved multiscale permutation entropy and least squares SVM, J. of Mechanical Science and Technology, 31 (6) (2017) 2711–2722.CrossRefGoogle Scholar
  19. [19]
    I. A. Abu–Mahfouz, A comparative study of three artificial neural networks for the detection and classification of gear faults, International J. of General Systems, 34 (3) (2005) 261–277.MathSciNetCrossRefzbMATHGoogle Scholar
  20. [20]
    G. Niu and B. S. Yang, Intelligent condition monitoring and prognostics system based on data–fusion strategy, Expert Systems with Applications, 37 (12) (2010) 8831–8840.CrossRefGoogle Scholar
  21. [21]
    H. Peng, F. Long and C. Ding, Feature selection based on mutual information: Criteria of max–dependency, maxrelevance, and min–redundancy, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (8) (2005) 1226–1238.CrossRefGoogle Scholar
  22. [22]
    X. Zhao, Data–driven fault detection, isolation and identification of rotating machinery: With applications to pumps and gearboxes, University of Alberta, Edmonton, Canada (2012).Google Scholar
  23. [23]
    A. Rai and S. H. Upadhyay, A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings, Tribology International, 96 (2016) 289–306.CrossRefGoogle Scholar
  24. [24]
    S. J. Dong, D. H. Sun, B. P. Tang, Z. Y. Gao, Y. R. Wang, W. T. Yu and M. Xia, Bearing degradation state recognition based on kernel PCA and wavelet kernel SVM, Proceedings of the Institution of Mechanical Engineers, Part C: J. of Mechanical Engineering Science, 229 (15) (2015) 2827–2834.Google Scholar
  25. [25]
    S. J. Dong and T. H. Luo, Bearing degradation process prediction based on the PCA and optimized LS–SVM model, Measurement, 46 (9) (2013) 3143–3152.CrossRefGoogle Scholar
  26. [26]
    L. Shuang and L. Meng, Bearing fault diagnosis based on PCA and SVM, Proceedings of 2007 International Conference on Mechatronics and Automation (2007) 3503–3507.CrossRefGoogle Scholar
  27. [27]
    O. R. Seryasat, H. G. Zadeh, M. Ghane, Z. Abooalizadeh, A. Taherkhani and F. Maleki, Fault diagnosis of ball–bearings using principal component analysis and support–vector machine, Life Science J., 10 (1) (2013) 393–397.Google Scholar
  28. [28]
    M. Li, The application of PCA and SVM in rolling bearing fault diagnosis, Advanced Materials Research, 430–432 (2012) 1163–1166.CrossRefGoogle Scholar
  29. [29]
    Z. F. Li and J. G. Li, Multichannel vibration fault diagnosis for rolling bearings based on QPCA and SVM, Advanced Materials Research, 199 (200) (2011) 927–930.Google Scholar
  30. [30]
    Y. Zhang, Y. Qin, Z. Y. Xing, L. M. Jia and X. Q. Cheng, Roller bearing safety region estimation and state identification based on LMD–PCA–LSSVM, Measurement, 46 (3) (2013) 1315–1324.CrossRefGoogle Scholar
  31. [31]
    G. F. Jia, S. F. Yuan and C. W. Tang, Fault diagnosis of roller bearing based on PCA and multi–class support vector machine, 4th IFIP International Conference on Computer and Computing Technologies in Agriculture and the 4th Symposium on Development of Rural Information (2011) 198–205.Google Scholar
  32. [32]
    X. Y. Yang, X. J. Zhou, W. B. Zhang and F. C. Yang, Rolling bearing fault diagnosis based on local wave method and KPCA–LSSVM, J. of Zhejiang University (Engineering Science), 44 (8) (2010) 1519–1524.Google Scholar
  33. [33]
    G. Tang, G. Li and H. Wang, Sparse component analysis based on support vector machine for fault diagnosis of roller bearings, International Conference on Sensing, Diagnostics, Prognostics, and Control (2017) 415–420.Google Scholar
  34. [34]
    F. Deng, S. Yang, Y. Liu, Y. Liao and B. Ren, Fault diagnosis of rolling bearing using the hermitian wavelet analysis, KPCA and SVM, International Conference on Sensing, Diagnostics, Prognostics, and Control, IEEE (2017) 632–637.Google Scholar
  35. [35]
    M. F. M. Yusof, C. K. E. Nizwan, S. A. Ong and M. Q. M. Ridzuan, Clustering of frequency spectrums from different bearing fault using principle component analysis, MATEC Web of Conferences, 90 (2017) 01006.CrossRefGoogle Scholar
  36. [36]
    Y. J. Cheng, H. Yuan, H. M. Liu and C. Lu, Fault diagnosis for rolling bearing based on SIFT–KPCA and SVM, Engineering Computations, 34 (1) (2017) 53–65.CrossRefGoogle Scholar
  37. [37]
    C. Wang, L. M. Jia and X. F. Li, Fault diagnosis method for the train axle box bearing based on KPCA and GA–SVM, Applied Mechanics & Materials, 441 (2014) 376–379.CrossRefGoogle Scholar
  38. [38]
    S. Nimityongskul and D. C. Kammer, Frequency domain model reduction based on principal component analysis, Mechanical Systems & Signal Processing, 24 (1) (2010) 41–51.CrossRefGoogle Scholar
  39. [39]
    Y. K. Gu, Z. X. Cheng and F. L. Zhu, Rolling bearing fault feature fusion based on principal component analysis and support vector machine, China Mechanical Engineering, 26 (20) (2015) 2778–2783.Google Scholar
  40. [40]
    X. Zhang, W. Lei and L. I. Bing, Bearing fault detection and diagnosis method based on principal component analysis and hidden markov model, J. of Xian Jiaotong University, 51 (6) (2017) 1–7.Google Scholar

Copyright information

© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Ying-Kui Gu
    • 1
  • Xiao-Qing Zhou
    • 1
  • Dong-Ping Yu
    • 1
  • Yan-Jun Shen
    • 1
  1. 1.School of Mechanical and Electrical EngineeringJiangxi University of Science and TechnologyGanzhou, JiangxiChina

Personalised recommendations